English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

While training on samples drawn from independent and identical distributionhas been a de facto paradigm for optimizing image classification networks,humans learn new concepts in an easy-to-hard manner and on the selectedexamples progressively. Driven by this fact, we investigate the trainingparadigms where the samples are not drawn from independent and identicaldistribution. We propose a data sampling strategy, named Drop-and-Refresh(DaR), motivated by the learning behaviors of humans that selectively drop easysamples and refresh them only periodically. We show in our experiments that theproposed DaR strategy can maintain (and in many cases improve) the predictiveaccuracy even when the training cost is reduced by 15% on various datasets(CIFAR 10, CIFAR 100 and ImageNet) and with different backbone architectures(ResNets, DenseNets and MobileNets). Furthermore and perhaps more importantly,we find the ImageNet pre-trained models using our DaR sampling strategyachieves better transferability for the downstream tasks including objectdetection (+0.3 AP), instance segmentation (+0.3 AP), scene parsing (+0.5 mIoU)and human pose estimation (+0.6 AP). Our investigation encourages people torethink the connections between the sampling strategy for training and thetransferability of its learned features for pre-training ImageNet models.

A Simple Non-i.i.d. Sampling Approach for Efficient Training and Better Generalization